Prof YU, Leung Ho Philip    楊良河 教授
Professor
Department of Mathematics and Information Technology
Contact
ORCiD
0000-0002-9449-0420
Phone
(852) 2948 7819
Email
plhyu@eduhk.hk
Address
10 Lo Ping Road, Tai Po, New Territories, Hong Kong
Website
https://pappl.eduhk.hk/rich/web/person.xhtml?pid=271389&name=YU, Leung Ho Philip
Scopus ID
7403599794
SDGs
3 - Good Health and Well-Being
4 - Quality Education
9 - Industry, Innovation and Infrastructure
10 - Reduced Inequality
17 - Partnerships for the Goals
ResearcherID
D-3154-2009
Research Interests
Data Science and AI, Preference Learning, AI in Education and Healthcare, Time Series Analysis, Statistical and AI Education.

Teaching Interests

Courses Taught in 2024-25:

MTH6184 Data Mining in STEM Education (MSc(AI&EdTech) course, 2nd semester)

External Appointments

Honorary Professor, Department of Computer Science, The University of Hong Kong, since 9/2020.

Personal Profile

Philip Yu is a Professor at the Department of Mathematics and Information Technology, and the Associate Director of the University Research Facility of Data Science and Artificial Intelligence at the Education University of Hong Kong. He currently serves as an Executive Committee Member of the International Association of Statistical Computing, and has previously held the Chairperson for the Asian Region Section of the International Association of Statistical Computing. Also, he has been the Vice President of the Hong Kong Statistical Society, a Council Member of the Hong Kong Mathematical Society, and a member of the Technical Committee of Computational Finance and Economics, IEEE Computational Intelligence Society. Professor Yu is also an Associate Editor for several journals, including Frontiers in Artificial Intelligence, Journal of Data Science, Statistics, and Visualisation, Journal of Applied Statistics, and Digital Finance. In 2009, he was elected as an Elected Member of the International Statistical Institute.

His current research interests include statistical methods and machine learning for ranking data, data mining in STEM Education, time series analysis, multimodal AI and its applications in education and healthcare. He has authored over 160 publications, including two well-reviewed research monographs on ranking methodology, and has received multiple international invention awards.

Professor Yu is dedicated to exemplary teaching and mentoring, providing outstanding service to the statistics and data science fields through numerous conferences and committee work. He actively promotes statistical and AI literacy in Hong Kong through outreach initiatives. With more than three decades of extensive experience, he has contributed to numerous contracted research/consulting projects and professional services for businesses, industries, and public bodies, including banks and insurance companies, stock exchanges, the Education Bureau (HKSAR), the Hong Kong Examinations and Assessment Authority, the Department of Health (HKSAR), the Hospital Authority, the Census and Statistics Department (HKSAR), and secondary schools.

Research Interests
Data Science and AI, Preference Learning, AI in Education and Healthcare, Time Series Analysis, Statistical and AI Education.

Teaching Interests

Courses Taught in 2024-25:

MTH6184 Data Mining in STEM Education (MSc(AI&EdTech) course, 2nd semester)

External Appointments

Honorary Professor, Department of Computer Science, The University of Hong Kong, since 9/2020.

Research Outputs
Scholarly Books, Monographs and Chapters
Chapter in an edited book (author)
楊良河和陳昊 (2022)。 淺談總體比例的置信區間估算法。輯於課程發展組編， 《學校數學通訊》，第 25 期， (頁 106-115)。香港: 香港特別行政區政府教育局課程發展處數學教育組。

Journal Publications
Publication in refereed journal
Zhuang, Y., Wang, C., and Yu, P.L.H. (2026). Preference modeling with multi-graph graph attention network. Neurocomputing, 660, Article 131872. https://doi.org/10.1016/j.neucom.2025.131872
Wang, X., Xin, L., and Yu, P.L.H. (2025). Matrix autoregressive time series with reduced-rank and sparse structural constraints. Journal of Forecasting. 44(8), 2442-2458. https://doi.org/10.1002/for.70019
Zhuang, Y., Zhao, R., Xie, Z., and Yu, P.L.H. (2025). Enhancing language learning through generative AI feedback on picture-cued writing tasks. Computers and Education: Artificial Intelligence, 9, Article 100450. https://doi.org/10.1016/j.caeai.2025.100450
Hui, R. W.-H., Chiu, K. W.-H., Lee, I.-C., Wang, C., Cheng, H.-M., Lu, J., Mao, X., Yu, S., Lam, L.-K., Mak, L.-Y., Cheung, T.-T., Chia, N.-H., Cheung, C.-C., Kan. W.-K., Wong, T. C.-L., Chan, A. C.-Y., Huang, Y.-H., Yuen, M.-F., Yu, P. L.-H., and Seto, W.-K. (2025). Multimodal multiphasic pre-operative image-based deep-learning predicts HCC outcomes after curative surgery. Hepatology. 82(2), 344-356. https://doi.org/10.1097/HEP.0000000000001180
Ullah, S., Chen, X., Han, H., Wu, J., Dong, J., Liu, R., Ding, W., Liu, M., Li, Q., Qi, H., Huang, Y., and Yu, P.L.H. (2025). A novel hybrid ensemble approach for wind speed forecasting with dual-stage decomposition strategy using optimized GRU and transformer models. Energy, 329, Article 136739. https://doi.org/10.1016/j.energy.2025.136739
Mao, X., Cheung, K.-S., Tan, J.-T., Mak, L.-Y., Lee, C.-H., Cheng, H. M., Hui, R.W.-H., Chan, E. W. Y., Yu, P.L.H., Yuen, M.-F., Leung, W. K. and Seto, W.-K. (2025). Risk of colorectal cancer and cancer-related mortality in type 2 diabetes patients treated with metformin, SGLT-2 inhibitors, or their combination. Cancer Communications, 45(7), 880-883. https://doi.org/10.1002/cac2.70028
Liu, J., Sun, D., Sun, J., Wang, J., & Yu, P. L. H. (2025). Designing a generative AI enabled learning environment for mathematics word problem solving in primary schools: Learning performance, attitudes and interaction. Computers and Education: Artificial Intelligence, 9, 100438. https://doi.org/10.1016/j.caeai.2025.100438
Peng, C., Yu, P.L.H., Lu, J., Cheng, H.M., Shen, X.P., Chiu, K.W.H., & Seto, W.K. (2025). Opportunistic detection of hepatocellular carcinoma using noncontrast CT and deep learning artificial intelligence. Journal of the American College of Radiology, 22(3), 249-259. https://doi.org/10.1016/j.jacr.2024.12.011
Ruggeri, F., Banks, D., Cleveland, W.S., Fisher, N.I., Escobar-Anel, M., Giudici, P., Raffinetti, E., Hoerl, R.W., Lin, D.K.J., Kenett, R.S., Li, W.K., Yu, P.L.H., Poggi, J., Reis, M.S., Saporta, G., Secchi, P., Sen, R., Steland, A., & Zhang, Z. (2025). Is there a future for stochastic modeling in business and industry in the era of machine learning and artificial intelligence?. Applied Stochastic Models in Business and Industry, 41 (2), Article e70004. https://doi.org/10.1002/asmb.70004
Wu, J., Chen, X., Dong, J., Tan, N., Liu, X., Chatzipavlis, A., Yu, P.L.H., Velegrakis, A., Wang, Y., Huang, Y., Cheng, H. & Wang, D. (2025). Dissolved oxygen prediction in the Dianchi River basin with explainable artificial intelligence based on physical prior knowledge. Environmental Modelling & Software, 188, Article 106412. https://doi.org/10.1016/j.envsoft.2025.106412
Zhao, J., Shang, C., Li, S., Xin, L. and Yu, P.L.H. (2025). Choosing the number of factors in factor analysis with incomplete data via a novel hierarchical Bayesian information criterion. Advances in Data Analysis and Classification, 19(1), 209-235. https://doi.org/10.1007/s11634-024-00582-w
Sun, D., Cheng, G., Yu, P. L. H., Jia, J., Zheng, Z., & Chen, A. (2025). Personalized stem education empowered by artificial intelligence: A comprehensive review and content analysis. Interactive Learning Environments, 1–23. https://doi.org/10.1080/10494820.2025.2462156
Yu, P.L.H., Chiu, K.W.H., Lu, J., Lui, G.C.S., Zhou, J., Cheng, H.M., Mao, X., Wu, J., Shen, X.P., Kwok, K.M., Kan, W.K., Ho, Y.C., Chan, H.T., Xiao, P., Mak, L.Y., Tsui, V.W.M., Hui, C., Lam, P.M., Deng, Z., Guo, J., Ni, L., Huang, J., Yu, S., Peng, C., Li, W.K., Yuen, M.F. & Seto, W.K. (2025). Application of a deep learning algorithm for the diagnosis of HCC. JHEP Reports, 7(1), Article 101219. https://doi.org/10.1016/j.jhepr.2024.101219
Tsui, E.L.H., Yu, P.L.H., Lam K.F., Poon, K.K.Y., Ng, A.C.M., Cheung, K.Y., Li, W., Leung, M.L.H., Lam, D.H.Y., Cheng, J.L.Y. & Ng, S.P.W. (2024). Development of a territory-wide household-based composite index for measuring relative distribution of households by economic status in individual small areas throughout Hong Kong. BMC Public Health, 24, Article 3555. https://doi.org/10.1186/s12889-024-21067-7
Lo, C.K., Yu, P.L.H., Xu, S., Ng, D.T.K. & Jong, M.S.Y. (2024). Exploring the application of ChatGPT in ESL/EFL education and related research issues: A systematic review of empirical studies. Smart Learning Environments, 11, Article 50. https://doi.org/10.1186/s40561-024-00342-5
Zhao, R., Zhuang, Y., Xie, Z. and Yu, P.L.H. (2024). Facilitating self-directed language learning in real-life scene description tasks with automated evaluation. Computers & Education. 219, 105106. https://doi.org/10.1016/j.compedu.2024.105106
Zhuang, Y., Li, D., Yu, P.L.H. & Li, W.K. (2024). On buffered moving average models. Journal of Time Series Analysis, 46(4), 599-622. https://doi.org/10.1111/jtsa.12778
Liang, L., Zhuang, Y., & Yu, P.L.H. (2024). Variable selection for high-dimensional incomplete data. Computational Statistics and Data Analysis, 192, 107877. https://doi.org/10.1016/j.csda.2023.107877
許志強和楊良河 (2024)。 數智時代大學生數字素養培育的實現路徑：以傳媒類專業大學生為例。 中國廣播電視學刊，2024(4)，40-45。 https://tra-oversea-cnki-net.ezproxy.eduhk.hk/KCMS/detail/detail.aspx?dbcode=CJFD&dbname=CJFDLAST2024&filename=GDXK202404008&uniplatform=OVERSEA&v=S8SMrkFldJgoYJBeY3NLunY3eELHajT5g677KKtf7LA3IOTz0lKnf90bm0jty8PLpublished version (EdUHK Users only)
Chen, X., Jiang, W., Qi, H., Liu, M., Ma, H., Yu, P.L.H., Wen, Y., Han, Z., Zhang, S. and Cao, G. (2024). Adaptive meta-knowledge transfer network for few-shot object detection in very high resolution remote sensing images. International Journal of Applied Earth Observation and Geoinformation, 127, 103675 https://doi.org/10.1016/j.jag.2024.103675
Zhao, R., Xie, Z., Zhuang, Y., & Yu, P.L.H. (2024). Automated quality evaluation of large-scale benchmark datasets for vision-language tasks. International Journal of Neural Systems, 34(3), 2450009. https://doi.org/10.1142/S0129065724500096
Chen, X., Li, L., Li, Z., Liu, M., Li, Q., Qi, H., Ma, D., Wen, Y., Cao, G. and Yu, P.L.H. (2024). KD loss: Enhancing discriminability of features with kernel trick for object detection in VHR remote sensing images. Engineering Applications of Artificial Intelligence, 129,107641 https://doi.org/10.1016/j.engappai.2023.107641
Zhao, R., Zhuang, Y., Zou, D., Xie, Q. & Yu, P.L.H. (2023). AI-assisted automated scoring of picture-cued writing tasks for language assessment. Education and Information Technologies, 28 (6), 7031-7063. https://doi.org/10.1007/s10639-022-11473-y
Gu, J., & Yu, P.L.H. (2023). Social order statistics models for ranking data with analysis of preferences in social networks. Annals of Applied Statistics, 17(1), 89-107. https://doi.org/10.1214/22-AOAS1617
Kuo, M. D., Chiu, K. W. H., Wang, D. S., Larici, A. R., Poplavskiy, D., Valentini, A., Napoli, A., Borghesi, A., Ligabue, G., Fang, X.H.B., Wong, H.K.C., Zhang, S., Hunter, J., Mousa, A., Infate, A., Elia, L., Golemi, S., Yu, P.L.H., Hui, C.K.M., & Erickson, B. J. (2023). Multi-center validation of an artificial intelligence system for detection of COVID-19 on chest radiographs in symptomatic patients. European Radiology, 33, 23-33 Doi:10.1007/s00330-022-08969-z.
Wang, X., Yu, P.L.H., Yang, W. and Su, J. (2022). Bayesian robust tensor completion via CP decomposition. Pattern Recognition Letters, 163, 121-128.
Gu, J., & Yu, P.L.H. (2022). Joint Latent Space Models for Ranking Data and Social Network. Statistics and Computing, 32, 1-15, Article 51. https://doi.org/10.1007/s11222-022-10106-1
Xin, L., Lam, K., & Yu, P.L.H. (2021). Effectiveness of filter trading as an intraday trading rule. Studies in Economics and Finance, 38(3), 659-674. https://doi.org/10.1108/SEF-09-2018-0294
Lu, R., & Yu, P.L.H. (2021). Buffered Vector Error-Correction Models: An Application to the U.S. Treasury Bond Rates. Studies in Nonlinear Dynamics & Econometrics, 25(5), 267-287. https://doi.org/10.1515/snde-2019-0047
You, J., Yu, P.L.H., Tsang, A.C.O., Tsui, E.L.H., Woo, P.P.S., Lui, C.S.M., Leung G.K.K., Mahboobani, N., Chu, C.-Y., Chong, W.-H., Poon, W.-L. (2021). 3D Dissimilar-Siamese-U-Net for Hyperdense Middle Cerebral Artery Sign Segmentation. Computerized Medical Imaging and Graphics, 90 (June 2021), 101898.
K.K.F. LAW, W.K. LI and Philip L.H. YU (2021). An Alternative Nonparametric Tail Risk Measure. Quantitative Finance, 21(4), 685-696.
Chiu, W. H. K., Vardhanabhuti, V., Poplavskiy, D., Yu, P. L. H., Du, R., Yap, A. Y. H., Zhang, S., Fong, A. H. T., Chin, T. W. Y., Lee, J. C. Y., Leung, S. T., Lo, C. S. Y., Lui, M. M. S., Fang, B. X. H., Ng, M. Y. and Kuo, M. D. (2020). Detection of COVID-19 Using Deep Learning Algorithms on Chest Radiographs. Journal of Thoracic Imaging, 35(6), 369-376.
Seto, W. K. W., Chiu, W. H. K., Yu, P. L. H., Cao, W., Cheng, H. M., Wong, E. M. F., Wu, J., Lui, G. C. S., Shen, X., Mak, L. Y., Li, W. K. and Yuen, R. M. F. (2020). An end-to-end artificial intelligence model accurately diagnosing hepatocellular carcinoma on computed tomography. United European Gastroenterology Journal, 8(8 suppl), 48-49.
Seto, W., Chiu, K., Yu, P. L. H., Cao, W., Cheng, H. M., Lui, G., Wong, E. M. F., Wu, J., Mak, L. Y., Shen, X. P., Li, W. K. and Yuen, M. F. (2020). High diagnostic performance of a deep learning artificial intelligence model in accurately diagnosing hepatocellular carcinoma on computed tomography. Hepatology, 72 (1 Suppl), 84-85.
Yu, P. L. H., Ng, F. C., and Ting, J. K. W. (2020). Adjusting covariance matrix for risk management. Quantitative Finance, 20(10), 1681-1699.
K.K.F. LAW, W.K. LI and Philip L.H. YU (2020). Evaluation Methods for Portfolio Management. Applied Stochastic Models in Business and Industry, 36(5), 857-876.
Lu, R., Yu, P. L. H., and Wang, X. (2020). Sparse vector error correction models with application to cointegration‐based trading. Australian & New Zealand Journal of Statistics, 62(3), 297-321.
K. LAW, W.K. LI and P. YU (2020). An Empirical Evaluation of Large Dynamic Covariance Models in Portfolio Value-at-Risk Estimation. Journal of Risk Model Validation, 14(2), 21-39.
Lu, R., and Yu, P. L. H. (2020). Smooth buffered autoregressive time series models. Journal of Statistical Planning and Inference, 206, 196-210.
You, J., Tsang, A. C. O., Yu, P. L. H., Tsui, E. L. H., Woo, P. P. S., Lui, C. S. M., and Leung, G. K. K. (2020). Automated hierarchy evaluation system of large vessel occlusion in acute ischemia stroke. Frontiers in Neuroinformatics, 14, 14.
Zhu, Y., Yu, P. L. H., and Mathew, T. (2020). Improved estimation of optimal portfolio with an application to the US stock market. Journal of Statistical Theory and Practice, 14(1), 25.
Tsang, A. C. O., You, J., Li, L. F., Tsang, F. C. P., Woo, P. P. S., Tsui, E. L. H., Yu, P. L. H. and Leung, G. K. K. (2020). Burden of large vessel occlusion stroke and the service gap of thrombectomy: A population-based study using a territory-wide public hospital system registry. International Journal of Stroke, 15(1), 69-74.
Publication in policy or professional journal
Yu P. L. H. and Li, W. K. (2021). Project-based Learning via Competition for Data Science Students. Harvard Data Science Review, 3(1), 1-4

Conference Papers
Invited conference paper
楊良河 (2022，6). 人工智能驅動的看圖造句自動評分。論文發表於「EDTECH教育科技研討會2022：特殊教育科技的創新和發展」，香港。
Refereed conference paper
Yip, J., Dong, C., Ling, M.H., Kwan, L.Y., Yu, P.L.H., Cheng, M.H., Lee, J.C.K. and Li, W.K. (2025). A data-analytic approach to early detection of at-risk students in higher education. In Proceedings of the 7th International Conference on Computer Science and Technologies in Education (CSTE 2025), Wuhan, China, pp.228-232. https://doi.org/10.1109/CSTE64638.2025.11092031
Yu, P.L.H., Zhuang, Y., Xie, Z., & Zhao, R. (2024, November). Enhancing Language Learning through AI-Generated Feedback on Picture-Cued Writing. [Paper presentation] The 21st AsiaCALL International Conference, Ha Noi, Vietnam. https://asiacall.info/the-21st-asiacall-international-conference/
Zhao, R., Xie, Z., Zhuang, Y., Li, H., & Yu, P.L.H. (2024, November). Enhancing Language Learning Through Multimodal AI-Driven Feedback on Picture Descriptions: An Eye-Tracking Study. [Paper presentation] 2024: ICCE 2024: The 32nd International Conference on Computers in Education, Philippines. https://library.apsce.net/index.php/ICCE
Gao, J., Xu, H., Shi, H., Ren, X., Yu, P.L.H., Liang, X., Jiang, X., & Li, Z. (2022, June). AutoBERT-Zero: Evolving BERT Backbone from Scratch. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), virtual. https://doi.org/10.1609/aaai.v36i10.21311
Gao, J., Zhou, Y., Yu, P.L.H., Joty, S., & Gu, J. (2022, June). UNISON: Unpaired Cross-Lingual Image Captioning. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), virtual. https://doi.org/10.1609/aaai.v36i10.21310
Seto, W.K.W., Chiu, K.H.K., Cao, W., Lui, G., Zhou, J. Cheng, H.M., Wu, J., Shen, X., Mak, L.Y., Huang, J., Li, W.K. and Yuen, R.M.F. & Yu, P.L.H. (2022). Training, validation and testing of a multiscale three-dimensional deep learning algorithm in accurately diagnosing hepatocellular carcinoma on computed tomography. Journal of Hepatology. Volume 77. Supplement 1, Abstracts of The International Liver Congress: London, United Kingdom, 22-26 June 2022, p. S78-S79.
Song, Y., Yu, P.L.H., Lee, J.C.K., Wu, K., & Cao, J. (2022, June). Developing an Avatar Generation System for the Metaverse in Education. Paper presented at The 1st International Workshop on Metaverse and Artificial Companions in Education and Society (MetaACES 2022), Hong Kong. https://www.eduhk.hk/metaaces2022/download/MetaACES%202022%20Program_20220622.pdf

Patents, Agreements, Assignments and Companies
Patents granted
Song, Y., Yu, L.H.P., Lee, J.C.K., Wu, K., & Cao, J. (2024). System and Method for Animating an Avatar in a Virtual World [Patent granted]. United States: United States Patent and Trademark Office.

Projects
Leveraging Generative AI for Adaptive Feedback Generation across Educational Stages in Enhancing Authentic Language Learning
Enabling students to understand vocabulary and use language in authentic contexts is essential for effective language learning. Recently, generative artificial intelligence (GenAI) technologies, such as multimodal large language models (MLLMs), have emerged as powerful tools to support this educational paradigm. By integrating the complementary nature of different modalities, such as images, texts, and speeches, MLLMs can provide learners with personalized, interactive learning experiences, like vocabulary learning through pictures and picture-cued writing. However, integrating these AI technologies into educational settings remains controversial. While many educators advocate for actively embracing AI, a one-size-fits-all approach may not address the diverse needs of all learners. General-purpose MLLMs can generate content that includes uncommon words, which may not be suitable for younger learners. Moreover, recent studies revealed that students may rely too much on AI technologies, ultimately harming their learning outcomes. Therefore, investigating how to effectively leverage the advantages of GenAI tools in enhancing language learning while mitigating potential drawbacks is a pressing concern that warrants further study. This two-year project aims to investigate the effective utilization of generative AI technologies to promote authentic language learning. Specifically, it will focus on supporting students in learning English by independently describing common objects and scenes from their daily lives. Initially, we will fine-tune an MLLM to evaluate students' writing across various educational stages and design strategies to generate feedback adaptively to enhance their learning while avoiding over-reliance on AI. Building on this foundation, we will develop a learning support system and recruit over 500 students from various educational stages in primary and secondary schools to participate in experimental research.
Project Start Year: 2025, Principal Investigator(s): YU, Leung Ho, Philip
SDGs Information: 4 - Quality Education
 
On the Multiple-Regime Hysteretic (Buffered) Time Series Models
The threshold time series models have emerged as a prominent class of nonlinear time series models over the past four decades. Recently, there has been growing interest in extending these models to incorporate hysteresis or a buffer zone to their regime-switching structure. While most of these hysteretic studies focus on two-regime models with a single threshold variable, there is a need for multiple regimes and multiple threshold variables in many economic and financial applications, especially for long time series or multivariate nonlinear time series. This project aims to extend hysteretic or buffered time series models that (1) incorporate multiple regimes; (2) support multiple threshold variables with flexible regime-switching structure, and (3) are easy to interpret.
Project Start Year: 2025, Principal Investigator(s): YU, Leung Ho, Philip
SDGs Information: 8 - Decent Work and Economic Growth
 
Revitalizing Mathematical Proficiency using AIScaffoldiaMaths: Empowering Students in Low-Resource Families through AI-Powered Supports in Informal Learning Environments
The proposed project aims to empower underprivileged children from low-resource families by leveraging AI and emerging technologies to enhance their mathematics knowledge and skills, foster critical competencies for self-directed learning, and improve affective domains such as confidence and attitudes toward maths in and after-school hours. In collaboration with Durham University, the project will: (1) develop a mathematics learning platform, AIScaffoldiaMaths, incorporating adaptive learning materials facilitated by AI-powered scaffoldings (2) implement this platform across 6 primary schools, reaching 300-500 disadvantaged students from Primary 3 to 6, and extend its use in local welfare and childcare programs. The project will unfold in two consecutive stages: Development & Implementation and Expansion. The system will be designed and developed based on an existing web-based maths system developed by team, with expending the functionality of adaptive learning materials and scaffoldings enabled by Generative AI such as Large Language Models for curriculum generation and optimization, video and audio content generation, and personalised AI avatar tutorial. Usability tests and experimental design will the system will be conducted to evaluate the system performance. Expected benefits include: (1) improved foundational mathematics education outcomes of primary school students; (2) the creation of an AI learning tool for maths education with a variety of resources and support mechanisms that enhance mathematics proficiency, scalable and sustainable over time; (3) a locally-developed AI innovation tailored to the specific needs of students and schools in Hong Kong; (4) a practical solution for bridging educational divides and fostering equity;(5) the establishment of sustainable collaborations with international experts in computer science and AI in education; and (6) enhanced understanding among university students of how design and develop AI tools facilitating personalized learning.
Project Start Year: 2025, Principal Investigator(s): SUN, Daner (YU, Leung Ho, Philip as Co-Investigator)
SDGs Information: 4 - Quality Education
 
AI-assisted Automated Scoring and Feedback System for Language Learning

Project Start Year: 2024, Principal Investigator(s): YU, Leung Ho, Philip

 
Investigating AI-driven Language Learning Using fNIRX and Eye Tracking

Project Start Year: 2024, Principal Investigator(s): YU, Leung Ho, Philip

 
LLM-powered Vocabulary Learning with Real-Life Situation Photos

Project Start Year: 2024, Principal Investigator(s): YU, Leung Ho, Philip

 
Preliminary Analysis of Real-World Time-Varying Rankings
..
Project Start Year: 2023, Principal Investigator(s): YU, Leung Ho, Philip

 
An Intelligent Platform for Desk Behavior Assessment via Joint Action and Attention Analysis

Project Start Year: 2022, Principal Investigator(s): YU, Leung Ho, Philip

 
An interactive avatar toolkit: Enhancing students’ online learning engagement in higher education
The project aims to develop and implement an interactive avatar (iAvatar) toolkit aligned with: (1) a framework of five dimensions of meaningful learning with technology, (2) the iAvatar toolkit design model, and (3) engagement to create a virtual interactive learning community.
Project Start Year: 2021, Principal Investigator(s): SONG, Yanjie (YU, Leung Ho, Philip as Co-Principal Investigator)

 
Bayesian Robust Tensor Completion via CP Decomposition
The real-world tensor data are inevitable missing and corrupted with noise. We propose a robust Bayesian tensor completion method, called MoG BTC-CP, which could impute the missing data and remove the complex noise simultaneously.
Project Start Year: 2021, Principal Investigator(s): WANG, Xiaohang (YU, Leung Ho Philip 楊良河 as Co-Principal Investigator)

 
Research and Development of Artificial Intelligence in Educational and Financial Technologies
..
Project Start Year: 2021, Principal Investigator(s): YU, Leung Ho, Philip

 
Research and Development of Artificial Intelligence in Educational and Financial Technologies (RMG)

Project Start Year: 2021, Principal Investigator(s): YU, Leung Ho, Philip

 
Moving Average for Buffered Time Series Modelling
The buffered time series model is a new type of nonlinear time series models that have attracted some attention in the literature. However, nearly all buffered time series models are of the autoregressive type. The objective of this project is to extend the buffered time series to include the moving average specification.
One paper has been submitted to a peer reviewed international journal for consideration for possible publication.
Project Start Year: 2021, Principal Investigator(s): LI, Wai Keung (YU, Leung Ho, Philip as Co-Investigator)

 
Cross-lingual Image Captioning
..
Project Start Year: 2020, Principal Investigator(s): YU, Leung Ho Philip 楊良河

 
Modeling Ranking Data in Social Networks
Ranking of items arises in many situations in our daily lives. Very often, not all the items are ranked, resulting in a set of incomplete ranking data. A typical example of incomplete ranking data is movie recommendation where users in a social media platform rated a number of movies and some of these users may be friends of each other. As not all movies are rated by the same user, after converting ratings to rankings, such dataset becomes a set of incomplete rankings with friendship connections among the users in a social network. It is known that individual choice behaviors may be influenced strongly from their peers or friends on social media. So far, traditional ranking models do not account for such spatial or network dependence. This project aims at developing new probabilistic models for ranking data in a social network. As individuals’ rank-order preference behaviors are often correlated with those of their “friends”, it is anticipated that the new models should be able to capture such social network effects and make better inferences, for instance, predicting ranks of the unranked items, inferring the latent social positions, and identifying latent groups. They
can help us to have a better understanding of some sociological phenomena such as homophily as well as the social patterns of the individuals and items. First of all, we develop conditional models of ranking data for a given social network by extending the traditional ranking models to incorporate peer effects. Secondly, we will adopt a latent space approach to model both ranking data and social network jointly. Under this approach, individuals and items are represented by points in a latent space, and the distance between two individual points and the distances from an individual point to the item points will then determine the likelihood of a connection between the two individuals and the probability of observing a ranking given by the individual respectively. One can also develop joint models by combining a marginal model for ranking data (social network) and a conditional model of social network (ranking data).
Efficient estimation procedures of the new models will be developed. To provide a comprehensive study under various conditions, the proposed models will be applied to analyze a number of real-world datasets and semi-synthetic datasets. It is believed that the new models can provide both practical and theoretical contributions to the analysis of ranking data in a social network.
Project Start Year: 2020, Principal Investigator(s): YU, Leung Ho Philip 楊良河

 
Contributing to the Development of Hong Kong into a Global Fintech Hub

Project Start Year: 2019, Principal Investigator(s): YU, Leung Ho Philip 楊良河

 
Prizes and awards
Gold Medal and Special Award
Automatic Multi-modal Deep Learning Analysis System
Date of receipt: /8/2025, Conferred by: International Invention Innovation Competition in Canada
 
Gold Medal
Reliable datasets are crucial for AI training, but evaluating ground-truth descriptions is error-prone. The invention automates this, offering quality, domain-specific feedback that improves AI model performance, effectiveness and quality control.
Date of receipt: /8/2025, Conferred by: Silicon Valley International Invention Festival 2025
 
Silver Medal
Prof YU Leung Ho Philip's "Automatic Multi-modal Dep Learning Analysis System" won a Silver Medal from the Geneva 2025
Date of receipt: /4/2025, Conferred by: International Exhibitions of Inventions Geneva 2025
 
Special Award

Date of receipt: /8/2022, Conferred by: International Invention Innovation Competition in Canada 2022
 
Gold Medal

Date of receipt: /8/2022, Conferred by: International Invention Innovation Competition in Canada 2022
 
Sliver Medal
Professor Yu's "UNISON: Unpaired Cross-lingual Image Captioning" won a Sliver Medal in 2022 Special Edition - Inventions Geneva Evaluation Days.
Date of receipt: 28/3/2022, Conferred by: 2022 Special Edition – Inventions Geneva Evaluation Days
 
Patents
Generative adversarial network-based lossless image compression model for cross-sectional imaging
This invention relates to high-resolution computerised tomography and, more particularly, to a generative adversarial network-based lossless image compression model for cross-sectional imaging. - A/A61
 
Generative adversarial network-based lossless image compression model for cross-sectional imaging
一種新的醫學圖像生成方法從厚切片電腦斷層掃描(CT)圖像合成為薄切片CT圖像作為輸入。 - A/A61
 
Multi-Scale 3D Convolutional Classification Model for Cross-Sectional Volumetic Image Recognition
This invention relates to three dimensional classification systems, methods of recognising cross-sectional images, and non-transitory machine-readable storage mediums. - A/A61